Latest VS Code update introduces prepackaged bundles of chat customizations that can include skills, commands, agents, MCP servers, and hooks.

Databricks' KARL agent uses reinforcement learning to generalize across six enterprise search behaviors — the problem that breaks most RAG pipelines.

Sophie Koonin discusses the realities of large-scale technical migrations, using Monzo’s shift to TypeScript as a roadmap. She explains how to handle "bends in the road," from documentation and ...

Databricks has released KARL, an RL-trained RAG agent that it says handles all six enterprise search categories at 33% lower cost than frontier models.